ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
☆83Jun 30, 2026Updated 2 weeks ago
Alternatives and similar repositories for ViVa
Users that are interested in ViVa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model☆321Jul 6, 2026Updated last week
- ☆24Apr 21, 2026Updated 2 months ago
- [CVPR 2026] HiF-VLA: An efficient, bidirectional spatiotemporal expansion Vision-Language-Action Model☆72Mar 11, 2026Updated 4 months ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,146Apr 3, 2026Updated 3 months ago
- Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons☆226Jul 1, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆263Jul 2, 2026Updated last week
- JAX Implementation for Q-Guided Flow and Common RL Baselines☆90Jun 18, 2026Updated 3 weeks ago
- SimX-OR: Extending Any Simulation Benchmark to Evaluate the Observational Robustness of VLA Models☆33Nov 4, 2025Updated 8 months ago
- Pi0-VLA Repository of "MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies"☆28Mar 9, 2026Updated 4 months ago
- ☆29Jun 30, 2026Updated 2 weeks ago
- Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer☆38Apr 17, 2026Updated 2 months ago
- EgoVerse: Egocentric Data for Robot Learning from Around the World☆460Updated this week
- [RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion☆278May 26, 2026Updated last month
- From Foundation to Application☆531Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos☆421Updated this week
- ☆93Jun 23, 2026Updated 3 weeks ago
- VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning☆162Oct 6, 2025Updated 9 months ago
- [IROS 2025] SIME: Enhancing Policy Self-Improvement with Modal-level Exploration☆17Mar 2, 2026Updated 4 months ago
- ☆21Updated this week
- An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.☆533Updated this week
- Official repo for "TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders"☆24Apr 9, 2026Updated 3 months ago
- NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards☆108Jan 11, 2026Updated 6 months ago
- [ACM MM'26] MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation☆63May 14, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.☆419Oct 10, 2025Updated 9 months ago
- Official Implementation of Paper: WMPO: World Model-based Policy Optimization for Vision-Language-Action Models☆223Jan 4, 2026Updated 6 months ago
- Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").☆93Jun 23, 2026Updated 3 weeks ago
- ActionCodec: What Makes for Good Action Tokenizers☆53Mar 1, 2026Updated 4 months ago
- ☆43Oct 31, 2025Updated 8 months ago
- [ICRA 2026] 🌠 DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation☆32Jan 14, 2026Updated 6 months ago
- ☆23Aug 22, 2025Updated 10 months ago
- ☆19Jun 26, 2025Updated last year
- ☆29May 22, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆52Jun 19, 2026Updated 3 weeks ago
- ReSemAct: Advancing Fine-Grained Robotic Manipulation via Semantic Structuring and Affordance Refinement☆17Jan 5, 2026Updated 6 months ago
- AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding☆46Jun 5, 2026Updated last month
- ICLR 2026 Paper: Ctrl-World☆537Apr 8, 2026Updated 3 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,582Updated this week
- This is the code repo of our work RoboNVS☆23Mar 31, 2026Updated 3 months ago
- Geo-Align: Video Generation Alignment via Metric Geometry Reward☆31May 25, 2026Updated last month